AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
uitbreidenos Skill Claude APIAnthropic Claude API: prompt caching, streaming, tool use, batch processing, model selection, cost optimization
- uitbreidenos Skill Playwright Pro
Playwright E2E testing: page object model, fixture setup, network interception, visual regression, CI integration, and debugging flaky tests — production-grade browser automation
- uitbreidenos Skill Vector Databases
- User is implementing semantic search, RAG pipelines, or recommendation systems
- uitbreidenos Skill 3 Statement Model
Three-statement financial model: income statement, balance sheet, cash flow statement — build integrated models, link statements, project financials, and stress-test assumptions
- uitbreidenos Skill Earnings Analysis
Earnings review workflow: parse transcript + filings, update model estimates, flag guidance changes, draft morning note — equity research patterns
- uitbreidenos Skill Dcf Model
DCF valuation: gather inputs from filings, build WACC, project FCF, terminal value, sensitivity table — patterns from Anthropic financial-services
- uitbreidenos Skill Ptc
Implement prompt-to-code workflows for rapid prototyping and code generation
- uitbreidenos Skill Agents Md
Generate AGENTS.md for cross-agent portability (Claude Code, Cursor, Codex, Gemini CLI). Tool-agnostic repo context document, distinct from CLAUDE.md.
- uitbreidenos Skill LLM Eval
LLM evaluation: build evaluation datasets, choose metrics (RAGAS, G-Eval, LLM-as-judge), run automated evals, monitor production quality, and detect regressions
- uitbreidenos Skill Agent Teams
Orchestrate multi-agent teams in Claude Code — set up coordinated sessions with task delegation, inter-agent communication, and parallel execution
- uitbreidenos Skill Pytorch Tensorflow
PyTorch and TensorFlow model training, data loaders, GPU setup, checkpointing, inference optimization
- uitbreidenos Skill Batch
Parallel agent orchestration: decompose large tasks into independent units, spawn background agents in worktrees, each opens a PR
- uitbreidenos Skill Valyu
Access paywalled research data via Valyu MCP: SEC EDGAR filings, PubMed papers, clinical trials, patents, financial reports.
- uitbreidenos Skill Chaos Test
Claude Code Chaos Test: adversarial test hardening. Spawns/orchestrates a Chaos Monkey agent to inject network drops, race conditions, and malformed inputs to harden infrastructure
- uitbreidenos Skill Cross Talk
Claude Code cross-talk (agent federation protocol): workflow guidelines, best practices, instructions, and integration examples
- uitbreidenos Skill MCP Client
Building an application that connects to and consumes MCP servers, or when the user mentions consuming MCP tools programmatically from their own ap...
- uitbreidenos Skill Agent Memory
Agent memory and context management: design persistent memory systems, manage context windows, implement summarization strategies, and build stateful agents that learn across sessions
- uitbreidenos Skill Model Router
Select optimal Claude model tier (Haiku/Sonnet/Opus) for any task using Mixture of Experts routing — 5 modes including tier classification, cascade escalation, parallel expert panel, domain routing, and budget governance
- uitbreidenos Skill Agent Sdk
Build AI agents using the Claude Agent SDK with tool use, memory, and multi-step orchestration
- uitbreidenos Skill Langgraph
LangGraph stateful agent framework: StateGraph, nodes, edges, conditional branching, persistence/checkpointing, human-in-the-loop, multi-agent subgraphs
- uitbreidenos Skill Agent Handoff
Implement structured handoffs between agents with JSON-based state transfer, conflict detection, and acknowledgment protocols
- uitbreidenos Skill Agent Tracing
Build observability into multi-agent systems with distributed traces, trace correlation, breakpoints, and execution replay
- uitbreidenos Skill Dag Scheduler
Build, validate, and execute directed acyclic graph (DAG) topologies for multi-agent workflows with automatic parallelization and cycle detection
- uitbreidenos Skill LLM Benchmark
LLM benchmarking: design benchmark suites, establish baselines, run A/B model comparisons, detect regressions, track production quality metrics, and create leaderboards for model selection
- uitbreidenos Skill Model Tiering
Automatically route and tier developer prompts across Opus, Sonnet, and Haiku based on task characteristics
- uitbreidenos Skill RAG Architect
RAG system design: chunking strategies, embedding model selection, vector store choice, retrieval patterns, reranking, evaluation — production-grade retrieval-augmented generation
- uitbreidenos Skill Swarm Sandbox
Safe isolated testing environment for multi-agent swarm topologies before production deployment
- uitbreidenos Skill Agent Construction
Multi-agent architecture, orchestrator patterns, tool design, agent loops, memory, error handling, handoffs
- uitbreidenos Skill MCP Server Builder
Build custom MCP servers: expose tools, resources, and prompts via stdio or HTTP/SSE transport — connect proprietary data to Claude Code
- uitbreidenos Skill Multi Agent Memory
Build shared, versioned memory systems for multi-agent teams using blackboard pattern, conflict resolution, and eventual consistency
- uitbreidenos Skill Prompt Engineering
Prompt engineering for production: few-shot prompting, chain-of-thought, system prompt design, output formatting, temperature settings, and evaluation — for Claude and other LLMs
- uitbreidenos Skill Graph Augmented Context
Claude Code Graph-Augmented Context (GAC): local SQLite codebase knowledge graph builder. Maps files, classes, functions, and import/dependency edges for advanced codebase RAG and contextual navigation
- uitbreidenos Skill Cash Flow Forecast
30-90 day cash flow forecasting for small businesses: model income and expenses, identify shortfalls, payroll runway, and early warning triggers
- uitbreidenos Skill Channels Event Streaming
Claude Code Channels: real-time event streaming between concurrent sessions, pub/sub patterns, event filtering, cross-session state synchronization, and reactive agent workflows
- uitbreidenos Skill Dispatch Background Jobs
Claude Code Dispatch: run long-running tasks as background jobs with progress polling, parallel sub-agent fan-out, result aggregation, and automatic retry on failure
- uitbreidenos Skill Prompt Caching
Optimize Claude API costs and latency with prompt caching strategies
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include claude-api, playwright-pro, vector-databases. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.